About the crop size

[yinhanxi]

When training,i set the crop size to 512×512 by default,but i have some problem with the pooling layer.
_lib/backbone/PSMNet/submodule.py_
_output_branch1 = self.branch1(output_skip)_
_RuntimeError: Given input size: (128x32x32). Calculated output size: (128x0x0). Output size is too small_
You set a larger size when training,right?Or there is another problem.
Thank you

[fabiotosi92]

Hi, the crop size should be set considering the aspect_ratio flag. In fact, crops are computed directly on the high-resolution images. Thus, if you want images at 512x512 as input of the network during training, you should set (for example) crop_width=2048 and crop_height=2048, aspect ratio=0.25. You can find some training scripts in the script folder.

[yinhanxi]

thankyou for sharing such a nice work^_^

[yinhanxi]

another question
Why Laplace and not Gauss
thankyou